11/07/23 – The Washington Post – AI Tools are Keeping Hospital Patients Alive
*Adams, Henry, Saria et al. Nature Medicine, 2022;
*Henry, Adams, Saria et al., Nature Medicine, 2022
In a recent Washington Post article, Leana S. Wen highlights the transformative impact of AI tools in healthcare, particularly in improving patient outcomes. The piece showcases Kaiser Permanente’s success in deploying an AI tool to identify early signs of patient deterioration in hospitals, a task traditionally reliant on clinician vigilance.
This AI system integrates various data points like vital signs and lab tests to alert healthcare teams proactively, helping in the early intervention of potential health crises. The results speak for themselves: a significant reduction in mortality rates. The article also notes the effective use of AI in other hospitals, such as Johns Hopkins, for early sepsis detection.
While Bayesian’s product is referenced in the discussion, the focus remains on the broader benefits and potentials of AI in healthcare.
Healthcare, like most other industries, has been experimenting with the use of large language models (LLMs) over the past year to streamline things like patient communication, clinical documentation and prior authorization.
While there has certainly been a great deal of hype recently surrounding LLMs and other forms of generative AI, there has also been a lot of skepticism. When it comes to an industry like healthcare, where one small technology failure could be the difference between life and death, many stakeholders are concerned about how to mitigate the risks associated with novel LLMs entering the field.
In this illuminating article written by Neri Cohen, MD PhD Chief Medical Informatics Officer at Bayesian Health, you’ll learn about the transformative impact of digital automation platforms on patient engagement and clinical outcomes.
Dr. Cohen dives into Bayesian Health’s groundbreaking AI platform, which empowers front-line clinicians by translating complex data sets into actionable insights. Developed in collaboration with Johns Hopkins, the platform has already demonstrated an 18.2% decrease in sepsis patient mortality rates and earned FDA designation as a Breakthrough Medical Device. With an adoption rate of 89% among clinicians, Bayesian’s platform is more than a technological marvel; it’s a tool clinicians trust to make data-backed decisions quickly. Dive deeper into the intersection of AI and healthcare, and explore how Bayesian Health is setting new industry standards for patient care.
Artificial intelligence (AI) has been making waves in various industries, and healthcare is no exception. As the potential of AI continues to unfold, experts have gathered at the recent 2023 STAT Breakthrough Summit to discuss its transformative impact on the healthcare system. Prominent figures in AI/ML: Nigam Shah, Suchi Saria, and Connor Landgraf shared their invaluable insights, shedding light on the four crucial ways in which the healthcare industry should shift its thinking regarding AI.
Amidst the increasing adoption of AI technologies, even the renowned “Godfather of AI,” Geoffrey Hinton, expressed concerns about the overwhelming power wielded by this disruptive technology. Recent months have witnessed a frenzy of efforts to harness AI in diverse sectors, and healthcare has been at the forefront of these groundbreaking endeavors.
As the boundaries of what is possible continue to be pushed, it becomes imperative for healthcare professionals, policymakers, and stakeholders to reflect on the optimal utilization of AI. This article explores the key takeaways from the discussions at the STAT Breakthrough Summit, offering insights into how the healthcare system should approach AI with a renewed mindset.
Read more about the four fundamental shifts in thinking that experts suggest are necessary for AI to truly revolutionize healthcare. By embracing these transformative concepts, the healthcare industry has the potential to unlock unprecedented advancements and redefine the standards of patient care.
Fantastic article from Stat, featuring Suchi Saria, PhD exploring the nuance of clinical AI, workflow orchestration, augmentation and other “sticky” issues swirling around artificial intelligence and machine learning.
Bayesian’s platform serves as a colleague / co-pilot for doctors and nurses. It empowers clinicians with real-time care signals to manage outcomes and cost while streamlining workflows to save time.
LifeBridge clinicians are forging the path forward for what great care looks like:
We’ve already been able to see improvement in early recognition rates, reduction in treatment delays, significant reductions in length of stay, reduction in alarm fatigue and financial gain conservatively projected to the tune of ~$2Mi+ per 200 beds! And we’ve begun to expand in areas beyond sepsis!*
Amid the challenges of calendar year 2022, one of the bright spots was the acceleration in artificial intelligence-related activity—both clinical and non-clinical—in healthcare.
“Careful examination of the sepsis tool implementations have found that, when Suchi Saria’s team at Bayesian Health looked closely at the success levels of sepsis-alert algorithms, they found that the actual rates of improvement in intervention turned out to be far more modest than they appeared at first glance.
In fact, she said, ‘I’ve seen incorrect evaluation. People measured sepsis for mortality, then deployed the tool, then used billing code data, and evaluated. But it looks as though you’ve improved mortality, but there’s a dilution effect.’” In other words, it’s turning out that clinician and clinical informatics leaders must necessarily test out and recalibrate any algorithms developed elsewhere, in their own organizations, since, as Patterson told me, clinicians document inside their own organizations’ electronic health records in individual ways.
12/20/22 Modern Healthcare – Navigating the ‘Wild West’ of AI adoption in healthcare
Right now, clinical AI adoption in healthcare can feel like the ‘wild west’ due to the lag in the regulator’s ability to keep pace with the dynamics within the marketplace. Consequently, health systems are taking matters into their own hands, forming internal guardrails to measure performance and substantiate AI investments across their clinical ecosystems. Ultimately, it comes down to innovation, risk-appetite and, most importantly, trust.
Our founder and CEO, Dr. Suchi Saria is quoted – “You can have the best technology in the world, but if [care teams] don’t trust it, they won’t use it, and you can’t see any benefit”.
CHAI co-founders Dr. Halamka and Dr. Anderson and CHAI member Suchi Saria of Bayesian Health discuss the importance and timeliness of CHAI’s mission, and share how the organization plans to prioritize patient safety, reliability, equity, transparency, and trust in the healthcare AI development process.
“AI as a field is evolving very rapidly. As a result, there is variable expertise amongst groups in how to go about implementing it correctly and evaluating whether what they’ve implemented is working. There is significant opportunity to accelerate AI adoption by sharing best practices and developing guardrails that the broader community (government, payor and provider groups) can benefit from.” Dr. Suchi Saria
11/20/22 Healthcare In Europe – Early detection of sepsis with the help of AI
Suchi Saria, PhD, director of the Machine Learning and Healthcare Lab at Johns Hopkins, who led this work, explains that TREWS automatically and continuously monitors disparate clinical data, including vital signs, laboratory data, medication history, procedure and clinical history, and physician notes. It generates a continuous real-time “sepsis score” that can trigger an alert to healthcare staff. Clinical caregivers can analyse why the TREWS alert was generated, accept or dismiss it, and initiate timely treatment on patients confirmed to be septic.
‘Our results showing high physician adoption and associated mortality and morbidity reductions are a milestone for the field of AI,’ comments Saria. ‘They are the culmination of nearly a decade of significant technological investment, deep collaboration, the development of novel techniques, and rigorous evaluation. Further, what’s most exciting here is that this approach is applicable not just to sepsis but to many other critical complications.’